423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix rlhf callback

Browse Source
This commit is contained in:
hiyouga
2023-11-16 03:26:19 +08:00
parent 856522a3df
commit 1817ffc86f
4 changed files with 19 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/hparams/finetuning_args.py
View File

@@ -166,7 +166,7 @@ class FinetuningArguments(FreezeArguments, LoraArguments, RLHFArguments):
if self.stage == "ppo" and self.reward_model is None:
raise ValueError("Reward model is necessary for PPO training.")
if self.reward_model_type == "lora" and self.finetuning_type != "lora":
if self.stage == "ppo" and self.reward_model_type == "lora" and self.finetuning_type != "lora":
raise ValueError("Lora reward model only supports lora training.")
def save_to_json(self, json_path: str):